|
Title:
|
CHATGPT IN SOFTWARE ENGINEERING: POTENTIALS, CHALLENGES AND POSSIBLE APPLICATIONS FOR UNIT TESTING AND CODE DEBUGGING |
|
Author(s):
|
Dominik Capellmann and Markus Westner |
|
ISBN:
|
978-989-8704-62 |
|
Editors:
|
Paula Miranda and Pedro Isaías |
|
Year:
|
2024 |
|
Edition:
|
Single |
|
Keywords:
|
ChatGPT, Software Engineering, Unit Testing, Code Debugging, Automated Testing, AI in Software Engineering, Design
Science Research |
|
Type:
|
Full |
|
First Page:
|
210 |
|
Last Page:
|
218 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
This research investigates the application of ChatGPT in software engineering, focusing on unit testing and code debugging,
using the Design Science Research methodology. Two artefacts have been developed to evaluate the performance of
different ChatGPT models, GPT-3.5 and GPT-4, under different configurations. The results show that GPT-4 outperforms
GPT-3.5 in both tasks, but at a higher cost due to increased token usage. Detailed prompts and lower temperature values
significantly improve the performance of GPT-3.5. Overall, the use of ChatGPT models proves to be highly useful for
automated unit testing and code debugging. |
|
|
|
|
|
|
